CN111665849A - Automatic driving system - Google Patents
Automatic driving system Download PDFInfo
- Publication number
- CN111665849A CN111665849A CN202010604416.XA CN202010604416A CN111665849A CN 111665849 A CN111665849 A CN 111665849A CN 202010604416 A CN202010604416 A CN 202010604416A CN 111665849 A CN111665849 A CN 111665849A
- Authority
- CN
- China
- Prior art keywords
- information
- module
- decision
- decision result
- sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 claims abstract description 67
- 230000007246 mechanism Effects 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 16
- 230000008447 perception Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 11
- 238000012550 audit Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
- G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Abstract
The present invention provides an automatic driving system, comprising: the first processing unit is used for acquiring current position information and first obstacle information, generating first decision result information and acquiring state information; the second processing unit is used for acquiring second obstacle information, steering information and speed information and generating second decision result information; comparing each piece of state information with a preset mechanism, and when any piece of state information is different from all pieces of information in the preset mechanism and the difference value between the first decision result information and the second decision result information is within a preset threshold value, marking the first decision result information as first credible information and storing the first credible information; when the difference value of the first decision result information and the second decision result information is not within the preset threshold value, planned parking is carried out according to the stored second credible information and the second decision result information, and the safety of the automatic driving system is improved.
Description
Technical Field
The invention relates to the field of design of automatic driving systems, in particular to an automatic driving system.
Background
With the rapid development of unmanned vehicle algorithms, theory, and information technology, automated driving has gradually moved from laboratories to the industry. New methods are continuously proposed in the core technical field of automatic driving such as perception, positioning, decision, control, software architecture and the like. The new software algorithms and architectures expand the capability boundaries and present significant challenges to autopilot safety.
Conventional automotive electrical and electronic systems are secured by functional safety systems, such as ISO 26262. The system requires a designer to analyze all potential failure conditions of software and hardware of the system and provides a corresponding processing mechanism. However, the L3 and higher automatic driving systems cannot apply the functional safety design system for the following reasons.
Firstly, due to the algorithm principle, it is difficult to effectively analyze and constrain the potential failure points of algorithms such as deep learning, and the algorithms are often key algorithms of the L3 and higher-level automatic driving systems.
Secondly, the automatic driving system must be capable of dealing with complex road conditions, and at present, it is difficult to perform exhaustive and failure analysis on all scenes which the automatic driving system needs to deal with according to a functional safety system.
Thirdly, in order to adapt to complex algorithms, a high-level automatic driving system usually adopts a computing platform, an operating system and support layer software which support multiple cores, so that the complexity of the system is further increased, and all potential problems cannot be analyzed and processed.
Finally, the code amount of the high-level automatic driving algorithm is far higher than that of the traditional automobile electronic software, and the cost for performing function safety certification on the high-level automatic driving algorithm is correspondingly increased.
Therefore, the conventional functional safety system is difficult to be applied to the automatic driving system of L3 and higher.
In order to solve the problems of the conventional functional security system, the following types are mainly used in the prior art.
The redundant system scheme mainly adopts two or more sets of automatic driving systems to carry out calculation simultaneously, judges whether a calculation error exists or not by comparing calculation results and makes a decision. The scheme requires a set of main automatic driving system to be deployed at the vehicle end; and one or more sets of slave systems are deployed at the cloud end or the vehicle end. If the difference value of the calculation results of the master system and the slave system is within the threshold value, controlling the vehicle according to the calculation result of the master system; and if the vehicle is out of the threshold value, controlling the vehicle to stop or to leave the driving environment as soon as possible, and stopping after entering a safe environment.
The decision and control system mutual supervision scheme mainly means that an automatic driving system is divided into a perception and decision subsystem and a control subsystem and respectively deployed in different domain controllers. The two are communicated through a controller area network CAN bus or an Ethernet bus, and the two supervise each other. Specifically, the supervision means generally performs the following operations by using heartbeat information: and if the local system operates normally, sending heartbeat to the opposite party. If the perception and decision subsystem has a problem, the control subsystem immediately stops; if the control subsystem has problems, the perception and decision system gives an alarm through sound and light.
However, the solutions in the prior art have the following problems:
for the scheme of the redundant system, firstly, if the master system and the slave system adopt the same algorithm, the problem of algorithm failure cannot be avoided; secondly, if the master system and the slave system adopt different algorithms, two sets of systems are required, the different algorithms always ensure smaller errors, and how to balance the calculation of the difference value among the multiple systems and the avoidance of the algorithm failure provides challenges for system design; third, the master-slave algorithm, if the same sensor scheme is adopted, may be affected by a single point failure of the sensor, while placing no requirements on the sensor security. Finally, if the redundant system is deployed in the cloud, each time the system computation needs to wait for the cloud result to return, processing delay and dependency are increased. In addition, the method does not provide a solution for the implementation of functional safety.
The decision and control system mutual supervision scheme has the following problems. Firstly, whether the sensing and decision subsystem works normally is judged by the sensing and decision subsystem, and the sensing and decision subsystem can be executed as long as the sensing and decision subsystem sends heartbeats normally, so that the safety of the whole system is limited by the sensing and decision subsystem and cannot reach the functional safety standard; second, the control subsystem may identify some risks by millimeter waves and ultrasound, but it does not provide a measure for each possible point of failure of the perception and decision subsystem. Thirdly, once the sensing and decision-making subsystem fails, safe parking cannot be realized in a complex environment only by the control system due to the limited sensing capability of the millimeter waves and the ultrasonic waves; finally, even if the subsequent technology is broken through, the perception and decision subsystem can achieve functional safety, and the authentication cost is high.
Disclosure of Invention
It is an object of embodiments of the present invention to provide an autopilot system that includes a first processing unit and a second processing unit. The first processing unit realizes the automatic driving function, the second processing unit carries out fault monitoring on the first processing unit, and carries out credible marking when the running state of the first processing unit is normal, and when the first processing unit has a fault, the second processing unit can plan parking so as to ensure that the automatic driving system realizes functional safety.
To solve the above problems, the present invention provides an automatic driving system including:
the first processing unit comprises a first positioning module, a first sensing module, a first decision module and a first state monitoring module; the first positioning module is connected with the positioning sensor and used for acquiring current position information; the first sensing module is connected with the first type sensor and used for acquiring first sensing information measured by the first type sensor and processing the first sensing information to obtain first obstacle information; the first decision module processes the first obstacle information and the current position information to generate first decision result information; the first state monitoring module is used for acquiring state information of the first sensing module, the first positioning module and the first decision module;
the second processing unit is connected with the first processing unit and comprises a second sensing module, a safety control module, a second decision module and a safety monitoring module; the second sensing module is connected with the second type sensor and used for acquiring second sensing information measured by the second type sensor and processing the second sensing information to obtain second obstacle information; the safety control module is connected with the bottom actuator and used for acquiring steering information and speed information fed back by the bottom actuator; the second decision module processes the second obstacle information, the steering information and the speed information to generate second decision result information; the security monitoring module is configured to compare each piece of state information with a preset mechanism, and when any piece of state information is different from all pieces of information in the preset mechanism and the second decision module determines that a difference value between the first decision result information and the second decision result information is within a preset threshold, the second decision module marks the first decision result information as first trusted information and stores the first trusted information; when the difference value of the first decision result information and the second decision result information is not within a preset threshold value, planning parking according to stored second credible information and the second decision result information; the second trusted information is previous trusted information of the first trusted information stored by the second processing unit.
Preferably, the safety monitoring module is further configured to, when any state information in the first sensing module, the first positioning module, and the first decision module is the same as any state information in a preset mechanism, perform parking planning by the second decision module according to the stored second credible information and the second decision result information.
Preferably, after comparing the first decision result information with the second decision result information, the second decision module sends a comparison result to the first decision module, the first decision module sends the comparison result to the first positioning module, the first positioning module sends the comparison result to the first sensing module, and the first positioning module and the first sensing module respectively perform fault judgment according to the comparison result.
Preferably, the state information includes information flows and processes of the first sensing module, the first positioning module and the first decision module, and a memory of the first processing unit.
Preferably, the first decision result information includes steering control information and torque control information for each waypoint in the planned path information planned based on the first obstacle information and the current position information.
Preferably, the first credible information includes current position information, first obstacle information and planning path information in the first decision result information.
Preferably, the first type of sensor includes a laser radar, a vision module, an ultrasonic radar, and a millimeter wave radar.
Preferably, the second type of sensor comprises a millimeter wave radar.
Preferably, the first processing unit and the second processing unit are connected through a high-speed serial computer expansion bus PCIE or an ethernet bus or a controller area network CAN bus.
The automatic driving system provided by the embodiment of the invention comprises a first processing unit and a second processing unit. The first processing unit realizes the automatic driving function, the second processing unit carries out fault monitoring on the first processing unit, and carries out credible marking when the running state of the first processing unit is normal, and when the first processing unit has a fault, the second processing unit can plan parking so as to ensure that the automatic driving system realizes functional safety.
Drawings
Fig. 1 is a schematic structural diagram of an automatic driving system according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be further noted that, for the convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Hereinafter, the first and second terms are merely used for distinguishing and have no other meaning.
Fig. 1 is a schematic structural diagram of an automatic driving system according to an embodiment of the present invention. The autonomous driving system may be applied in an autonomous driving vehicle. As shown in fig. 1, the automatic driving system includes: a first processing unit 100 and a second processing unit 200.
The first processing unit 100 includes a first positioning module 101, a first sensing module 102, a first decision module 103, and a first status monitoring module 104. The first positioning module 101 is connected with a positioning sensor and used for acquiring current position information; the first sensing module 102 is connected to the first type sensor, and is configured to acquire first sensing information measured by the first type sensor, and process the first sensing information to obtain first obstacle information; the first decision module 103 processes the first obstacle information and the current position information to generate first decision result information; the first status monitoring module 104 is configured to obtain status information of the first positioning module 101, the first sensing module 102, and the first decision module 103.
The Positioning sensor may be a Global Positioning System (GPS). The first type of sensor includes a laser radar, a vision module, an ultrasonic radar, and a millimeter wave radar.
The second processing unit 200 is connected with the first processing unit 100, and comprises a second sensing module 201, a safety control module 202, a second decision module 203 and a safety monitoring module 204; the second sensing module 201 is connected to the second type sensor, and is configured to acquire second sensing information measured by the second type sensor, and process the second sensing information to obtain second obstacle information; the safety control module 202 is connected with the bottom layer actuator and used for acquiring steering information and speed information fed back by the bottom layer actuator; the second decision module 203 processes the second obstacle information, the steering information and the speed information to generate second decision result information; the security monitoring module 204 is configured to compare each piece of state information with a preset mechanism, and when any piece of state information is different from all pieces of information in the preset mechanism and the second decision module 203 determines that a difference value between the first decision result information and the second decision result information is within a preset threshold, the second decision module 203 marks the first decision result information as first trusted information and stores the first trusted information; when the difference value of the first decision result information and the second decision result information is not within a preset threshold value, planning parking according to the stored second credible information and the second decision result information; the second trusted information is previous trusted information of the first trusted information stored by the second processing unit 200.
Wherein the second type of sensor may be a millimeter wave radar. The bottom layer actuator can be an automatic driving bottom layer vehicle controller and is mainly used for controlling a steering system, a braking system and a power system of the automatic driving vehicle, and the bottom layer actuator can also be connected with a wheel speed meter to acquire speed information of the vehicle and also can acquire steering information fed back by the steering system.
Specifically, the first processing unit 100 may be understood as a functional core, and the second processing unit 200 may be understood as a secure core. The function core is mainly used for realizing an automatic driving function, and the safety core is mainly used for guaranteeing.
Since the function core is mainly responsible for the function of the automatic driving, the function core can adopt complex algorithms such as a deep learning algorithm, a heuristic algorithm and the like to perform decision processing, and is not directly related to the safety which can be achieved by the whole automatic driving system. However, the above algorithms are generally difficult to meet functional safety standards through exhaustion, process control, and the like. Taking the deep learning algorithm as an example, the failure points existing in the calculation cannot be analyzed and guaranteed due to the fact that a theoretical system is not complete. Thus, detection of a failed node of the algorithm of the functional core may be performed by a secure core physically isolated from the functional core.
The functional core and the security core can be respectively deployed in different hardware computing platforms to ensure that the functional core and the security core work independently and do not interfere with each other. The functional core and the security core CAN be connected by any one of a Peripheral Component Interconnect Express (PCIE), an ethernet bus, and a Controller Area Network (CAN) bus.
The following description will take an example in which the first processing unit 100 is a functional core and the second processing unit 200 is a secure core.
First, the first positioning module 101 converts the sensing signal of the GPS into the current position information of the autonomous vehicle, and sends the current position information to the first sensing module 102.
The first sensing module 102 obtains sensing information of each sensor in the first type of sensor, the sensing information is collectively referred to as first sensing information, then, the first sensing information is processed to obtain first obstacle information, and then the first obstacle information and the current position information are sent to the first decision module 103.
The first decision module 103 calculates the current position information of the autonomous vehicle and the first obstacle information to obtain first decision result information, and sends the first decision result information to the second decision module 203. The first decision result information may be steering control information and torque control information of each waypoint in the planned path information planned by the first decision module 103 according to the first obstacle information and the current position information.
Wherein the first decision result information is time-sensitive. In one particular embodiment, for example, the functional core plans more than 100m of route information at a time, which can support control of the vehicle for a future period of time. It should be noted that the length of time that is supported is related to the speed of the autonomous vehicle and the complexity of the environment.
Meanwhile, a key link realized by the automatic driving system can be provided with a monitoring point, so that the monitoring of the key link is realized by monitoring the monitoring point in real time. The key links may cover the memory usage of the first processing unit 100 in the operating system, the support layer, and the automatic driving system, and the operating status of each module in the first processing unit 100. The first status monitoring module 104 obtains status information such as memory usage, information flow, and process monitored by the monitoring point in the above-mentioned key link, for example, can obtain information flow and process of the key link such as the first positioning module 101, the first sensing module 102, and the first decision module 103, and memory usage of the first processing unit 100.
After receiving the status information sent by the first status monitoring module 104, the security monitoring module 204 compares the status information with a preset mechanism, and determines whether the operating status of each module of the first processing unit 100 is normal. The preset mechanism may be a preset blacklist mechanism, and the blacklist mechanism includes information of information flow exception, process exception and memory exception.
By way of example and not limitation, for information flow, the security monitoring module 204 may first determine whether the calculation result of each main module is erroneous. Secondly, the logic of the calculation result of the main module is determined, for example, whether the current position information acquired by the first positioning module 101 jumps, whether the obstacle acquired by the first sensing module 102 flashes frequently, and whether the information flow is interrupted, such as too long information flow delay or too short information flow time. Whether the fixed point jumps or not means that the position information has a certain rule, theoretically, the jump is within a certain numerical range, and if the numerical jump exceeding the certain range happens, the jump is considered. If a large jitter of a short time is detected, the information flow is abnormal.
For a process, the security monitoring module 204 may determine whether a process exception, such as a process crash, or a process interrupt, exists.
For the memory, the security monitoring module 204 may determine whether the memory is insufficient, for example, whether the memory occupancy rate exceeds a preset threshold, where the preset threshold is an empirical value, for example, 85%.
In one specific embodiment, an autonomous vehicle suddenly jumps to 10 meters in 1 second at point a, and is not expected to be based on current speed estimates, i.e., the calculation logic is considered problematic. I.e. to indicate that there is an anomaly in the information flow.
In another specific embodiment, if the vehicle speed information corresponding to the current location information exceeds a physically reachable value, or the timestamp of the vehicle speed information is a value several processing cycles ago, the security monitoring module 204 determines that there is an anomaly in the information flow.
In summary, if the security monitoring module 204 determines that any state information of the monitoring point is inconsistent with all information in the blacklist mechanism after processing, the subsequent audit is continued, and at this time, the security monitoring module 204 may send a notification message for instructing to audit to the second decision module 203 to instruct the second decision module 203 to perform the audit. The safety core can determine that the functional core is in a normal state after the audit is passed. The auditing of the application refers to auditing of the first decision result information.
In a specific embodiment, the second decision module 203 of the security core may calculate to obtain second decision result information according to the second obstacle information, the steering information and the speed information, compare the second decision result information with the first decision result information, and if the difference is within a preset threshold, the second decision module 203 marks the first decision result information as trusted information to be stored; if the difference value is not within the preset threshold value, the second decision module 203 takes the trusted information obtained at the previous moment and the information of the second decision result as the main basis for safe parking. The second decision result information may be steering control information and torque control information of the autonomous vehicle. The trusted information may include current location information, obstacle information, and path information.
Here, a credible flag may be added to the first decision result information, and the first decision result information to which the credible flag is added is referred to as credible information, and the credible flag may be a character identifier, such as binary "1".
The method is mainly used for obtaining and storing the credible information in a mode of combining a preset mechanism and audit. In case the first processing unit 100 is out of function at the next time, the credible information can be used as one of the important bases for planning the parking at the next time.
Further, the safety monitoring module 204 is further configured to, when any state information of the first sensing module 102, the first positioning module 101, and the first decision module 103 is the same as any information of a preset mechanism, perform parking planning by the second decision module 203 according to the stored second credible information and the stored second decision result information. Therefore, the safety core can independently carry out emergency parking treatment under the condition that the function core is abnormal, and the safety of the whole automatic driving system is ensured.
The status information acquired by the first status monitoring module 104 is sent to the safety monitoring module 204 in real time, so that when the functional core has a problem, the safety monitoring module 204 stops receiving the calculation result of the functional core and feeds the calculation result back to the second decision module 203, so as to prevent the wrong result from being marked as the trusted information by the second decision module 203, thereby improving the safety of the autonomous vehicle.
At this time, if the security monitoring module 204 obtains that any state information of the first sensing module 102, the first positioning module 101, and the first decision module 103 is the same as any information of the preset mechanism, the security monitoring module 204 may send a notification message for indicating that auditing cannot be performed to the second decision module 203, so that the second decision module 203 plans to stop the vehicle after receiving the notification message.
Further, if the second decision module 203 intends to plan parking, at this time, the second decision module 203 may further compare the first decision result information with the second decision result information, and send the comparison result to the first decision module 103, the first decision module 103 sends the comparison result to the first positioning module 101, the first positioning module 101 sends the comparison result to the first sensing module 102, and the first positioning module 101 and the first sensing module 102 perform fault judgment according to the comparison result, respectively, thereby being beneficial to the first positioning module 101 and/or the first sensing module 102 in the functional core to perform fault judgment of various sensors connected thereto, respectively, to determine whether the sensor connected thereto fails, and thus promoting improvement of safety of the automatic driving system.
The automatic driving system provided by the embodiment of the invention comprises a first processing unit and a second processing unit. The first processing unit realizes an automatic driving function, the second processing unit carries out fault monitoring on the first processing unit, and carries out credibility marking when the running state of the first processing unit is normal, and when the first processing unit breaks down, the second processing unit can plan parking according to credibility information and first decision result information at the last moment without depending on the first processing unit, and the second processing unit can independently carry out emergency parking processing, so that the safety of the whole automatic driving system is ensured.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. An autopilot system, the autopilot system comprising:
the first processing unit comprises a first positioning module, a first sensing module, a first decision module and a first state monitoring module; the first positioning module is connected with the positioning sensor and used for acquiring current position information; the first sensing module is connected with the first type sensor and used for acquiring first sensing information measured by the first type sensor and processing the first sensing information to obtain first obstacle information; the first decision module processes the first obstacle information and the current position information to generate first decision result information; the first state monitoring module is used for acquiring state information of the first sensing module, the first positioning module and the first decision module;
the second processing unit is connected with the first processing unit and comprises a second sensing module, a safety control module, a second decision module and a safety monitoring module; the second sensing module is connected with the second type sensor and used for acquiring second sensing information measured by the second type sensor and processing the second sensing information to obtain second obstacle information; the safety control module is connected with the bottom actuator and used for acquiring steering information and speed information fed back by the bottom actuator; the second decision module processes the second obstacle information, the steering information and the speed information to generate second decision result information; the security monitoring module is configured to compare each piece of state information with a preset mechanism, and when any piece of state information is different from all pieces of information in the preset mechanism and the second decision module determines that a difference value between the first decision result information and the second decision result information is within a preset threshold, the second decision module marks the first decision result information as first trusted information and stores the first trusted information; when the difference value of the first decision result information and the second decision result information is not within a preset threshold value, planning parking according to stored second credible information and the second decision result information; the second trusted information is previous trusted information of the first trusted information stored by the second processing unit.
2. The automatic driving system according to claim 1, wherein the safety monitoring module is further configured to, when any state information of the first sensing module, the first positioning module and the first decision module is the same as any information of a preset mechanism, perform parking planning by the second decision module according to the stored second credible information and the second decision result information.
3. The automatic driving system according to claim 1, wherein the second decision module compares the first decision result information with the second decision result information, and then sends a comparison result to the first decision module, the first decision module sends the comparison result to the first positioning module, the first positioning module sends the comparison result to the first sensing module, and the first positioning module and the first sensing module perform failure determination according to the comparison result, respectively.
4. The autopilot system of claim 1 wherein the status information includes information flow and progress of the first perception module, the first location module and the first decision module, memory of the first processing unit.
5. The automatic driving system according to claim 1, wherein the first decision result information includes steering control information and torque control information for each waypoint in planned path information planned based on the first obstacle information and current position information.
6. The autopilot system of claim 1 wherein the first trusted information includes planned path information in current location information, first obstacle information, and first decision result information.
7. The autopilot system of claim 1 wherein the first type of sensor includes a lidar, a vision module, an ultrasonic radar, and a millimeter wave radar.
8. The autopilot system of claim 1 wherein the second type of sensor includes millimeter wave radar.
9. The autopilot system of claim 1 wherein the first processing unit and the second processing unit are connected by a high speed serial computer expansion bus PCIE or an ethernet bus or a controller area network, CAN, bus.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010604416.XA CN111665849B (en) | 2020-06-29 | 2020-06-29 | Automatic driving system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010604416.XA CN111665849B (en) | 2020-06-29 | 2020-06-29 | Automatic driving system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111665849A true CN111665849A (en) | 2020-09-15 |
| CN111665849B CN111665849B (en) | 2023-08-01 |
Family
ID=72390146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010604416.XA Active CN111665849B (en) | 2020-06-29 | 2020-06-29 | Automatic driving system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111665849B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180921A (en) * | 2020-09-22 | 2021-01-05 | 安徽江淮汽车集团股份有限公司 | Automatic driving algorithm training system and method |
| CN112249033A (en) * | 2020-10-30 | 2021-01-22 | 广州小鹏自动驾驶科技有限公司 | Automatic driving system and method for vehicle |
| CN113401139A (en) * | 2021-06-21 | 2021-09-17 | 安徽江淮汽车集团股份有限公司 | Tandem type automatic driving system |
| CN114550476A (en) * | 2021-11-30 | 2022-05-27 | 深圳元戎启行科技有限公司 | Data processing method, vehicle management platform and computer readable storage medium |
| CN114604260A (en) * | 2022-05-11 | 2022-06-10 | 青岛慧拓智能机器有限公司 | Domain controller and domain control device for unmanned vehicle |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013087514A1 (en) * | 2011-12-16 | 2013-06-20 | Renault S.A.S. | Control of the autonomous mode of bimodal vehicles |
| US20160368491A1 (en) * | 2013-07-04 | 2016-12-22 | Robert Bosch Gmbh | Method and device for operating a motor vehicle in an automated driving mode |
| CN108776472A (en) * | 2018-05-17 | 2018-11-09 | 驭势（上海）汽车科技有限公司 | Intelligent driving control method and system, onboard control device and intelligent driving vehicle |
| CN108958248A (en) * | 2018-07-05 | 2018-12-07 | 北京智行者科技有限公司 | Standby system |
| CN109460042A (en) * | 2018-12-29 | 2019-03-12 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot control method and system |
| CN109991987A (en) * | 2019-04-29 | 2019-07-09 | 北京智行者科技有限公司 | Automatic Pilot decision-making technique and device |
| CN110481565A (en) * | 2019-08-20 | 2019-11-22 | 北京三快在线科技有限公司 | The control method of automatic driving vehicle and the control device of automatic driving vehicle |
| CN110568847A (en) * | 2019-08-30 | 2019-12-13 | 驭势科技（北京）有限公司 | Intelligent control system and method for vehicle, vehicle-mounted equipment and storage medium |
| CN209928279U (en) * | 2018-04-25 | 2020-01-10 | 长沙智能驾驶研究院有限公司 | Intelligent driving system and intelligent vehicle |
| CN110929431A (en) * | 2020-02-03 | 2020-03-27 | 北京三快在线科技有限公司 | Training method and device for vehicle driving decision model |
-
2020
- 2020-06-29 CN CN202010604416.XA patent/CN111665849B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013087514A1 (en) * | 2011-12-16 | 2013-06-20 | Renault S.A.S. | Control of the autonomous mode of bimodal vehicles |
| US20160368491A1 (en) * | 2013-07-04 | 2016-12-22 | Robert Bosch Gmbh | Method and device for operating a motor vehicle in an automated driving mode |
| CN209928279U (en) * | 2018-04-25 | 2020-01-10 | 长沙智能驾驶研究院有限公司 | Intelligent driving system and intelligent vehicle |
| CN108776472A (en) * | 2018-05-17 | 2018-11-09 | 驭势（上海）汽车科技有限公司 | Intelligent driving control method and system, onboard control device and intelligent driving vehicle |
| CN108958248A (en) * | 2018-07-05 | 2018-12-07 | 北京智行者科技有限公司 | Standby system |
| CN109460042A (en) * | 2018-12-29 | 2019-03-12 | 北京经纬恒润科技有限公司 | A kind of automatic Pilot control method and system |
| CN109991987A (en) * | 2019-04-29 | 2019-07-09 | 北京智行者科技有限公司 | Automatic Pilot decision-making technique and device |
| CN110481565A (en) * | 2019-08-20 | 2019-11-22 | 北京三快在线科技有限公司 | The control method of automatic driving vehicle and the control device of automatic driving vehicle |
| CN110568847A (en) * | 2019-08-30 | 2019-12-13 | 驭势科技（北京）有限公司 | Intelligent control system and method for vehicle, vehicle-mounted equipment and storage medium |
| CN110929431A (en) * | 2020-02-03 | 2020-03-27 | 北京三快在线科技有限公司 | Training method and device for vehicle driving decision model |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180921A (en) * | 2020-09-22 | 2021-01-05 | 安徽江淮汽车集团股份有限公司 | Automatic driving algorithm training system and method |
| CN112249033A (en) * | 2020-10-30 | 2021-01-22 | 广州小鹏自动驾驶科技有限公司 | Automatic driving system and method for vehicle |
| CN112249033B (en) * | 2020-10-30 | 2022-02-01 | 广州小鹏自动驾驶科技有限公司 | Automatic driving system and method for vehicle |
| CN113401139A (en) * | 2021-06-21 | 2021-09-17 | 安徽江淮汽车集团股份有限公司 | Tandem type automatic driving system |
| CN113401139B (en) * | 2021-06-21 | 2023-02-17 | 安徽江淮汽车集团股份有限公司 | Tandem type automatic driving system |
| CN114550476A (en) * | 2021-11-30 | 2022-05-27 | 深圳元戎启行科技有限公司 | Data processing method, vehicle management platform and computer readable storage medium |
| CN114604260A (en) * | 2022-05-11 | 2022-06-10 | 青岛慧拓智能机器有限公司 | Domain controller and domain control device for unmanned vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111665849B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111665849A (en) | Automatic driving system | |
| CN107908186B (en) | Method and system for controlling operation of unmanned vehicle | |
| US11360864B2 (en) | Vehicle safety electronic control system | |
| US10940867B2 (en) | Substitution of sensor measurement data | |
| US9566966B2 (en) | Method for carrying out a safety function of a vehicle and system for carrying out the method | |
| CN109358591B (en) | Vehicle fault processing method, device, equipment and storage medium | |
| US10532740B2 (en) | Method and arrangement for monitoring and adapting the performance of a fusion system of an autonomous vehicle | |
| US20170080950A1 (en) | Method and device for operating a vehicle | |
| CN110035939B (en) | Vehicle control device | |
| CN106054852B (en) | Fault-tolerant construction is measured in integrated fault silencing and failure movement system | |
| CN110785742A (en) | Device and method for actuating a vehicle module as a function of a status signal | |
| US11279380B2 (en) | Method and apparatus for detecting and avoiding collision applied to vehicle | |
| JP2019128639A (en) | Electronic control device | |
| WO2023050586A1 (en) | Abnormality detection method and apparatus for positioning sensor, and terminal device | |
| US20210089018A1 (en) | Method for controlling a motor vehicle remotely | |
| KR101914624B1 (en) | Processor for preventing accident of automatic driving system and method of the same | |
| CN113879324B (en) | Intelligent driving vehicle sensor fault processing method and device | |
| CN114485630A (en) | Wheel speed redundancy detection method, wheel speed redundancy detection system, wheel speed redundancy detection equipment and storage medium | |
| US11529962B2 (en) | Autonomous driving assistance system and operation method therefor | |
| JP3788168B2 (en) | Vehicle travel support device | |
| CN115973180A (en) | Steering detection method, apparatus, device and medium for autonomous vehicle | |
| JP2021018563A (en) | Automatic driving operation planning device, automatic driving operation planning method, and automatic driving operation planning program | |
| CN114771555A (en) | Autonomous parking fault diagnosis method and device and unmanned vehicle | |
| Lee et al. | Development of an emergency control algorithm for a fail-safe system in automated driving vehicles | |
| CN115237105A (en) | Unmanned vehicle positioning abnormity detection method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant before: Beijing Idriverplus Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |